ClawAudit verdict
article-workflow
Article analysis and archival workflow that fetches URLs, analyzes content, and stores results in Feishu; data boundary declarations are explicit, credentials are Feishu integration tokens used for the stated archival purpose.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (6)
Recursive delete from root or home — destructive command
docs/MIGRATION.md · code · rm -rf ~
Possible hardcoded credential
docs/字段映射优化.md · code · token="YOUR_TOKEN
Accesses shell history/config
docs/CONFIG_PROTECTION.md · code · ~/.zshrc
Pipe to python — executes piped content as Python code
docs/MIGRATION.md · prose · downgraded · | python3
Python aiohttp session — async network access
core/cover_extractor.py · prose · downgraded · aiohttp.ClientSession
Python os.environ.get — reads environment variable
scripts/config_manager.py · prose · downgraded · os.environ.get(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/F). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.